Water conservancy monitoring based on visual sensor networks

Wireless visual sensor network (VSN) can be said to be a special class of wireless sensor network (WSN) with smart-cameras. Due to its visual sensing capability, it has become an effective tool for applications such as large area surveillance, environmental monitoring and objects tracking. Different from a conventional WSN, VSN typically includes relatively expensive camera sensors, enhanced flash memory and a powerful CPU. While energy consumption is dominated primarily by data transmission and reception, VSN consumes extra power onimage sensing, processing and storing operations. The well-known energy-hole problem of WSNs has a drastic impact on the lifetime of VSN, because of the additional energy consumption of a VSN. Most prior research on VSN energy issues are primarily focusedon a single device or a given specific scenario. In this paper, we propose a novel optimal two-tier deployment strategy for a large scale VSN. Our two-tier VSN architecture includes tier-1 sensing network with visual sensor nodes (VNs) and tier-2 network having only relay nodes (RNs). While sensing network mainly performs image data collection, relay network only for wards image data packets to the central sink node. We use uniform random distribution of VNs to minimize the cost of VSN and RNs are deployed following two dimensional Gaussian distribution so as to avoid energy-hole problem. Algorithms are also introduced that optimizes deployment parameters and are shown to enhance the lifetime of the VSN in a cost effective manner.

Recently much research has been conducted in visual sensor networks. Compared to traditional sensor networks, vision networks differ in various aspects such as the amount of data to be processed and transmitted, the requirements on quality-of-service, and the level of collaboration among the sensor nodes. This paper deals with sensor fusion on visual sensor networks. We focus here on methods for fusing data from various distributed sensors and present a generic framework for fusion on embedded sensor nodes. This paper extends our previous work on distributed smart cameras and presents our approach toward the transformation of smart cameras into a distributed, embedded multisensor network. Our generic fusion model has been completely implemented on a distributed embedded system. It provides a middleware which supports automatic mapping of our fusion model to the target hardware. This middleware features dynamic reconfiguration to support modification of the fusion application at runtime without loss of sensor data. The feasibility and reusability of the I-SENSE concept is demonstrated with experimental results of two case studies: vehicle classification and bulk good separation. Qualitative and quantitative benefits of multilevel information fusion are outlined in this article.

Modern developments in image technology enabled easy access to an innovative type of sensor-based networks, Camera or Visual Sensor Networks (VSN). Nevertheless, more sensor data sources bring about the problem of overload information. To solve this problem, some researchers have been carried out on the techniques to counteract the data overload caused by sensors without losing useful data. The aim of fusion in each application is to combine images from several sensors, which leads to the decreased amount of input image data, producing an image with more accurate data. This paper proposes a noisy feature removal scheme for multi-focus image fusion combining the decision information of optimized individual features. The proposed scheme is developed in two main steps. In the first step, the diverse types of features are extracted from each block of input blurred images. The useful information of these individual features indicates which image block is more focused among corresponding blocks in source images. After that, noisy features are removed using binary Genetic Grey wolf optimizer (GGWO) algorithm. The ensemble decision based on individual features is employed to fuse blurred images in the second step. The experimentation is evaluated on different multi-focus images and it reveals that GGWO based proposed method performs better visual quality than other methods.

Wireless sensor networks are an important research area that has attracted a lot of attention in the past few years. Most of this attention, however, has focused on wireless sensor network collect scalar data such as temperature and vibration. Scalar data is insufficient for many applications such as video surveillance and traffic monitoring. Whereas, camera sensors collect video data, which are rich in information and offer tremendous potential when used in wireless sensor networks. Video sensor networks continue to gain increase interest due to their ability to collect video information for a wide range of applications in recent years. However, knowledge about these types of networks is mostly related to visual algorithms, leaving the issues such as the coverage of video sensor network and the transmission of video data aside. In this paper, we first highlight the issues and opportunities of video sensor network. And then we discuss key research issue on video sensor network, specifically camera coverage problem, network architecture, and low-power video data processing and communication. Finally, we identify enabling approaches in this area.

Visual Sensor Networks (VSNs), formed by large number of low-cost, small-size visual sensor nodes, represent a new trend in surveillance and monitoring practices. Sensor collaboration is essential to VSNs and normally performed among sensors having similar measurements. The directional sensing characteristics of imagers and the presence of visual occlusion present unique challenges to neighborhood formation, as geographically-close neighbors might not monitor similar scenes. In this paper, we propose the concept of forming semantic neighbors, where collaboration is only performed among geographically-close nodes that capture similar images, thus requiring image comparison as a necessary step. To avoid large amount of data transfer, we propose feature-based image comparison as features provide more compact representation of the image. The paper studies several representative feature detectors and descriptors, in order to identify a suitable feature-based image comparison system for the resource-constrained VSN. We consider two sets of metrics from both the resource consumption and accuracy perspectives to evaluate various combinations of feature detectors and descriptors. Based on experimental results obtained from the Oxford dataset and the MSP dataset, we conclude that the combination of Harris detector and moment invariants presents the best balance between resource consumption and accuracy for semantic neighbor formation in VSNs.

A prediction-based approach for features aggregation in Visual Sensor Networks

Wireless Sensor Network future direction is going towards more complex sensor such as camera sensor. Therefore, a very active research field is Visual Sensor Network. This type of network brings new challenges such as processing and transmitting a massive amount of data generated by the camera sensor. The efforts into decreasing the amount of data to be transmitted are going towards two directions: data encoding and data filtering. This chapter introduces an algorithm for each direction. Visual data encoding is performed by means of Predictive Video Encoding using Phase-Only Correlation function to achieve motion estimation. Visual data filtering is done at the lowest level of abstraction and is performed in three phases: pixel classification, background update and detection. The algorithms involved in each phase are light in terms of complexity and memory resources.

The wide availability of embedded sensor platforms and low-cost cameras—together with the developments in wireless communication—make it now possible the conception of pervasive intelligent systems based on vision. Such systems may be understood as distributed and collaborative sensor networks, able to produce, aggregate and process images in order to understand the observed scene and communicate the relevant information found about it. In this paper, we investigate the peculiarities of visual sensor networks with respect to standard vision systems and we identify possible strategies to accomplish image processing and analysis tasks over them. Although the rather strong constraints in computational and transmission power of embedded platforms that may prevent the use of state of the art computer vision and pattern recognition methods, we argue that multi-node processing methods may be envisaged to decompose a complex task into a hierarchy of computationally simpler problems to be solved over the nodes of the network. These ideas are illustrated by describing an application of visual sensor network to infomobility. In particular, we consider an experimental setting in which several views of a parking lot are acquired by the sensor nodes in the network. By integrating the various views, the network is capable to provide a description of the scene in terms of the available spaces in the parking lot.

The ever increasing use of plant protection chemicals (PPCs) has been on the constant rise as the agriculture industry tries to keep up with growing demand. Excessive usage of PPCs leads to smaller profit margins for farmers as well as damage to ecosystems. An internet of things based visual sensor network was developed to feed data into a neural network classifier which would detect the early onset of plant disease. The sensor network was deployed at a farm owned and run by Wilkin & Sons, a soft fruit grower based in Essex, UK. A prototype convolutional neural network was developed with the purpose of classifying 3 types of images; healthy plants, powdery mildew affected plants and leaf scorch affected plants. The classifier was able to reach an accuracy of 95.48 % for late stage disease detection through images alone.

When visual sensor networks (VSNs) enter daily life in society, they not only bring great convenience but also cause people to worry about privacy. Traditional image encryption uses the snowflake effect to protect the privacy, but this can compromise the usability of directly browsing images captured by nodes in VSNs. Recently, thumbnail-preserving encryption (TPE) has been proposed to balance image usability and privacy. However, the Markov chain’s limited connectivity and high time cost, which result in low efficiency, may preclude its application in VSNs. Motivated by this, we propose a novel TPE scheme to protect the image collected in VSNs’ privacy efficiently. We first deeply study the bijective relationship between the three-pixel group and its rank, and then propose a new number method for both, based on which we design the efficient rank mapping. Subsequently, an efficient thumbnail-preserving image encryption via three-pixel rank mapping (E-TPE) is designed, achieving NR security and enhancing the Markov chain’s connectivity. The experiments demonstrate the scheme’s efficiency; that is, it is currently the quickest ideal-TPE scheme with NR security, and a good balance is achieved between usability and privacy.

Recent developments in image and video technologies enabled easy access to a new type of sensor-based networks, Visual Sensor Networks (VSN). VSNs are gaining a lot of attention lately. They are used in several applications including surveillance and telepresence. They consist of several low-cost, low-power visual nodes with sensing, data processing, and communication capabilities. These tiny nodes are able to collect large volumes of images, process them, and send extracted data to each other and to the base station for further analysis. Unfortunately, the huge amount of data captured and processed is faced with the limited resources of such platforms. There are several challenges involved with the design and implementation of VSNs. This chapter presents an overview of visual nodes, architectures, and challenges. It also reviews available VSN platforms and compares their processing capabilities, highlighting the need for new lightweight but efficient image processing algorithms and architectures.

In this work, we propose the cubature Kalman filter (CKF) based distributed object tracking algorithm in a visual sensor network (VSN). A VSN consists of several distributed smart cameras having the ability to process and analyze the retrieved data locally. The first objective is to optimize the tracking process within the VSN through the CKF. Under the conditions of non-linear motion and observation model, the CKF based method features a considerably better tracking accuracy than the extended Kalman filter (EKF) based method in terms of the mean square error (MSE). Although, the particle filter (PF) based method shows better performance than the CKF, it is computationally very complex. The second objective is to optimize the object tracking by aggregating the tracking results from multiple cameras. Assuming the VSN is a multi-camera network with overlapping field of views (FOVs), cameras having the same object in their FOV exchange their local estimates of the object's position and velocity. During the estimation process, each of the participating cameras aggregates the received states via a consensus algorithm. Thus, the object's real state is more accurately predicted by the resulting joint state than it would be by processing only a single camera's observation.

Nowadays visual sensor networks are used in emergency or time of surveillance of remote area where human reach is not possible. There situations arise when mobility of nodes is required in visual sensor network. In this paper we considers mobility of visual sensor nodes and tries to maximize the lifetime of network using priority if nodes. We use hierarchical and heterogeneous architecture for deploying nodes. In this we use two types of nodes. On this architecture we use prioritized scheduling technique to maximize the lifetime of network. Result shows lifetime is increased compare to the stationary nodes as after same time we get more live sensors than stationary system.

During the last decade, visual monitoring has gained an increasing interest especially in the field of smart cities and intelligent transportation systems. This paper describes a feature-based vehicle tracking system in visual sensor networks at roundabouts. In the proposed system, the tasks for vehicle tracking are divided among smart camera nodes and the receiver. Smart camera nodes are embedded devices equipped with camera sensor, multiprocessors for video processing and computer vision tasks, and an RF transceiver for wireless communication. They are responsible for the vehicle detection and classification as well as features extraction. In order to satisfy the constraints of the visual sensor network in terms of power and communication resources, we assume that only the features are transmitted to the sink node. The received features will then be used to retrieve the vehicle trajectories. In order to train the vehicle classifier used at the camera nodes and to test the proposed tracking approach, a training database was built by placing cameras around a realworld roundabout. The system is shown to be capable of tracking vehicles even in partial occlusion cases.

This paper is to study the tracking of mobile objects and associated coverage problems in visual sensor networks. When sensors equipped with cameras are randomly deployed in a monitoring environment, many cameras are involved in covering the same mobile object. Images of the object may be captured by different camera nodes in different orientations simultaneously, and the captured images are then sent back to a base station or server. However, achieving characteristic point coverage of objects invariably involves a great deal of redundant image data consuming the transmission energy of the visual sensor network. One approach is proposed to overcome this problem. The minimum number of camera nodes required for set coverage can be determined by predicting the direction and speed of the mobile object. The simulation results show that this protocol reduces transmission cost while preserving the maximum coverage range of mobile objects.